Integrating Active Learning and Contextually Guide for Semantic Labeling of LiDAR Point Cloud

Abstract

To alleviate the difficulties in obtaining training data sets of 3D point clouds, an active learning (AL) framework is proposed to iteratively select a small portion of unlabeled points to query their labels, and creates a minimum manually-annotated training set. To handle the biased sampling problem caused by category imbalance and local similarities, a neighbor-consistency prior is used to conduct an unbiased sampling for selecting the value samples into the training set. Additionally, to reduce the number of categories used in labeling, a higher-order MRF containing a regional label cost term, is exploited to refine the labeling results.